fw14k / README.md
sabareesh88's picture
Update README.md
9d5c9da verified
metadata
license: mit
datasets:
  - HuggingFaceFW/fineweb
library_name: Transformers
pipeline_tag: text-generation

This is a Llama 2 architecture model series trained on the FineWeb dataset. This is ~500 Million model uses lamma tokenizer. trained using code from Karpathy lamma2